Fast Single Image Dehazing Using Iterative Bilateral Filter

• Published in: 2010 2nd International Conference on Information Engineering and Computer Science pp. 1 - 4
• Main Authors: Sun Kang, Wang Bo, Zheng Zhihui, Zhou Zhiqiang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2010
• Subjects: Channel estimation; Cost function; Equations; Filtering algorithms; Image color analysis; Mathematical model; Pixel
• DOI: 10.1109/ICIECS.2010.5678374
• ISBN: 1424479398; 9781424479399
• ISSN: 2156-7379

In this paper, we present a simple but efficient iterative method for increasing scene visibility and recovering haze-free scene contrast from a single hazy image. Using the dark channel prior with the haze imaging model, we directly estimate the coarse transmission map at first, then an iterative refinement module based on bilateral filter is applied to refine the transmission map. The main advantage of our algorithm compared with others is its speed and efficiency for both color and gray level images. At last, a comparative study with other state-of-art algorithms is proposed to demonstrate that similar or better quality results of our scheme are obtained with only a tiny fraction time consumption.